arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.10428eess.AS
收藏

如何训练你的耳朵:面向大动态范围输入和轻至重度听力损失的听觉模型仿真

How to train your ears: Auditory-model emulation for large-dynamic-range inputs and mild-to-severe hearing losses

Peter Leer, Jesper Jensen, Zheng-Hua Tan, Jan Østergaard, Lars Bramsløw

AI总结:

本研究提出一种嵌入频率与电平依赖性的新优化目标,以提升深度神经网络对听觉模型的仿真性能,尤其针对大动态范围输入和轻至重度听力损失,且不增加推理计算负担。

摘要:

先进的听觉模型在设计与听力损失补偿或语音增强相关的信号处理算法时非常有用。此类听觉模型能够提供对听觉通路的丰富而详细的描述,并可能基于生理测量实现信号处理策略的个体化。然而,这些听觉模型通常计算需求高,需要大量时间进行计算。为解决这一问题,先前的研究已探索使用深度神经网络来仿真听觉模型并减少推理时间。尽管这些深度神经网络在计算时间方面带来了显著的效率提升,但它们可能面临仿真性能随听觉模型频率通道和输入声压级变化而不均匀的问题,使其在许多任务中不适用。在本研究中,我们证明现有最先进方法中使用的传统机器学习优化目标是这一局限性的主要来源。具体而言,该优化目标未能考虑听觉模型的频率依赖性和电平依赖性,这些依赖性由大输入动态范围以及听觉模型所仿真的不同类型听力损失引起。为克服这一局限,我们提出了一种新的优化目标,该目标明确嵌入了听觉模型的频率依赖性和电平依赖性。我们的结果表明,这一新的优化目标显著提高了深度神经网络在相关输入声级和听觉模型频率通道上的仿真性能,且未增加推理期间的计算负担。解决这些局限性对于推进听觉模型在信号处理任务中的应用至关重要,确保其在多样化场景中的有效性。

英文摘要:

Advanced auditory models are useful in designing signal-processing algorithms for hearing-loss compensation or speech enhancement. Such auditory models provide rich and detailed descriptions of the auditory pathway, and might allow for individualization of signal-processing strategies, based on physiological measurements. However, these auditory models are often computationally demanding, requiring significant time to compute. To address this issue, previous studies have explored the use of deep neural networks to emulate auditory models and reduce inference time. While these deep neural networks offer impressive efficiency gains in terms of computational time, they may suffer from uneven emulation performance as a function of auditory-model frequency-channels and input sound pressure level, making them unsuitable for many tasks. In this study, we demonstrate that the conventional machine-learning optimization objective used in existing state-of-the-art methods is the primary source of this limitation. Specifically, the optimization objective fails to account for the frequency- and level-dependencies of the auditory model, caused by a large input dynamic range and different types of hearing losses emulated by the auditory model. To overcome this limitation, we propose a new optimization objective that explicitly embeds the frequency- and level-dependencies of the auditory model. Our results show that this new optimization objective significantly improves the emulation performance of deep neural networks across relevant input sound levels and auditory-model frequency channels, without increasing the computational load during inference. Addressing these limitations is essential for advancing the application of auditory models in signal-processing tasks, ensuring their efficacy in diverse scenarios.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑